Effective compressed sensing MRI reconstruction via hybrid GSGWO algorithm

Abstract

In a bio-imaging context, the main issues which obstruct the CS (Compressed sensing) application are image reconstruction time and computational cost. This paper presents an effective compressed sensing-based MRI reconstruction through a hybrid optimization algorithm. Initially, the preprocessing stage is performed using Cross guided bilateral filter. Then the K-space is generated by the Fourier transform. The hybrid Walsh Hadamard Transform and Discrete Wavelet Transform (HWHDWT) is utilized for the compressive sensing of the images. Finally, the Hybrid Galactic Swarm Optimization and Grey Wolf Optimization (HGSGWO) algorithm are developed for MRI reconstruction. The dataset collected from a hospital which contains MRI images both in JPEG and DICOM format. The performance of SSIM (Structural Similarity Index), PSNR (Peak Signal to Noise Ratio), MSE (mean square error) and reconstruction time are evaluated for images and it is compared with the existing methods.